net/netvsc: bug fixes and runtime queue reconfiguration

index 6584819f4f..798b4c9023 100644
@@ -1433,6 +1433,7 @@ eth_hn_dev_uninit(struct rte_eth_dev *eth_dev)
 {
 	struct hn_data *hv = eth_dev->data->dev_private;
 	int ret, ret_stop;
+	int i;
 
 	PMD_INIT_FUNC_TRACE();
 

@@ -1444,6 +1445,15 @@ eth_hn_dev_uninit(struct rte_eth_dev *eth_dev)
 
 	hn_detach(hv);
 	hn_chim_uninit(eth_dev);
+
+	/* Close any subchannels before closing the primary channel */
+	for (i = 1; i < HN_MAX_CHANNELS; i++) {
+		if (hv->channels[i] != NULL) {
+			rte_vmbus_chan_close(hv->channels[i]);
+			hv->channels[i] = NULL;
+		}
+	}
+
 	rte_vmbus_chan_close(hv->channels[0]);
 	rte_free(hv->primary);
 	ret = rte_eth_dev_owner_delete(hv->owner.id);

index 798b4c9023..9f61f3a1a5 100644
@@ -1455,7 +1455,6 @@ eth_hn_dev_uninit(struct rte_eth_dev *eth_dev)
 	}
 
 	rte_vmbus_chan_close(hv->channels[0]);
-	rte_free(hv->primary);
 	ret = rte_eth_dev_owner_delete(hv->owner.id);
 	if (ret != 0)
 		return ret;

index 9f61f3a1a5..19721b4829 100644
@@ -1376,8 +1376,10 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
 	hv->primary = hn_rx_queue_alloc(hv, 0,
 					eth_dev->device->numa_node);
 
-	if (!hv->primary)
-		return -ENOMEM;
+	if (!hv->primary) {
+		err = -ENOMEM;
+		goto failed;
+	}
 
 	err = hn_attach(hv, RTE_ETHER_MTU);
 	if  (err)

@@ -1403,8 +1405,10 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
 
 	max_chan = rte_vmbus_max_channels(vmbus);
 	PMD_INIT_LOG(DEBUG, "VMBus max channels %d", max_chan);
-	if (max_chan <= 0)
+	if (max_chan <= 0) {
+		err = max_chan ? max_chan : -ENODEV;
 		goto failed;
+	}
 
 	if (hn_rndis_query_rsscaps(hv, &rxr_cnt) != 0)
 		rxr_cnt = 1;

@@ -1425,6 +1429,8 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
 
 	hn_chim_uninit(eth_dev);
 	hn_detach(hv);
+	rte_free(hv->primary);
+	rte_vmbus_chan_close(hv->channels[0]);
 	return err;
 }
 

index 19721b4829..5e954b8812 100644
@@ -1043,16 +1043,22 @@ hn_dev_start(struct rte_eth_dev *dev)
 				      NDIS_PACKET_TYPE_BROADCAST |
 				      NDIS_PACKET_TYPE_ALL_MULTICAST |
 				      NDIS_PACKET_TYPE_DIRECTED);
-	if (error)
+	if (error) {
+		rte_dev_event_callback_unregister(NULL,
+						  netvsc_hotadd_callback, hv);
 		return error;
+	}
 
 	error = hn_vf_start(dev);
-	if (error)
+	if (error) {
 		hn_rndis_set_rxfilter(hv, 0);
+		rte_dev_event_callback_unregister(NULL,
+						  netvsc_hotadd_callback, hv);
+		return error;
+	}
 
 	/* Initialize Link state */
-	if (error == 0)
-		hn_dev_link_update(dev, 0);
+	hn_dev_link_update(dev, 0);
 
 	for (i = 0; i < hv->num_queues; i++) {
 		dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STARTED;

index 5e954b8812..45d69272aa 100644
@@ -1214,6 +1214,11 @@ hn_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (ret)
 		return ret;
 
+	/* Free chimney bitmap and rxbuf_info before NVS detach */
+	hn_chim_uninit(dev);
+	rte_free(hv->primary->rxbuf_info);
+	hv->primary->rxbuf_info = NULL;
+
 	/* Release channel resources */
 	hn_detach(hv);
 

@@ -1222,6 +1227,7 @@ hn_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		rte_vmbus_chan_close(hv->channels[i]);
 
 	/* Close primary vmbus channel */
+	rte_vmbus_chan_close(hv->channels[0]);
 	rte_free(hv->channels[0]);
 
 	/* Unmap and re-map vmbus device */

@@ -1248,13 +1254,17 @@ hn_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rte_vmbus_set_latency(hv->vmbus, hv->channels[0], hv->latency);
 
 	ret = hn_reinit(dev, mtu);
-	if (!ret)
+	if (!ret) {
+		hn_chim_init(dev);
 		goto out;
+	}
 
 	/* In case of error, attempt to restore original MTU */
 	ret = hn_reinit(dev, orig_mtu);
 	if (ret)
 		PMD_DRV_LOG(ERR, "Restoring original MTU failed for netvsc");
+	else
+		hn_chim_init(dev);
 
 	ret = hn_vf_mtu_set(dev, orig_mtu);
 	if (ret)

index 45d69272aa..78ad566309 100644
@@ -745,6 +745,9 @@ netvsc_hotadd_callback(const char *device_name, enum rte_dev_event_type type,
 	}
 }
 
+static void hn_detach(struct hn_data *hv);
+static int hn_attach(struct hn_data *hv, unsigned int mtu);
+
 static int hn_dev_configure(struct rte_eth_dev *dev)
 {
 	struct rte_eth_conf *dev_conf = &dev->data->dev_conf;

@@ -754,6 +757,8 @@ static int hn_dev_configure(struct rte_eth_dev *dev)
 	struct hn_data *hv = dev->data->dev_private;
 	uint64_t unsupported;
 	int i, err, subchan;
+	uint32_t old_subchans = 0;
+	bool device_unmapped = false;
 
 	PMD_INIT_FUNC_TRACE();
 

@@ -778,36 +783,111 @@ static int hn_dev_configure(struct rte_eth_dev *dev)
 
 	hv->vlan_strip = !!(rxmode->offloads & RTE_ETH_RX_OFFLOAD_VLAN_STRIP);
 
-	err = hn_rndis_conf_offload(hv, txmode->offloads,
-				    rxmode->offloads);
-	if (err) {
-		PMD_DRV_LOG(NOTICE,
-			    "offload configure failed");
-		return err;
-	}
+	/* If queue count unchanged, skip subchannel teardown/reinit */
+	if (RTE_MAX(dev->data->nb_rx_queues,
+		    dev->data->nb_tx_queues) == hv->num_queues)
+		goto skip_reinit;
 
 	hv->num_queues = RTE_MAX(dev->data->nb_rx_queues,
 				 dev->data->nb_tx_queues);
 
+	/* Close all existing subchannels */
+	for (i = 1; i < HN_MAX_CHANNELS; i++) {
+		if (hv->channels[i] != NULL) {
+			rte_vmbus_chan_close(hv->channels[i]);
+			hv->channels[i] = NULL;
+			old_subchans++;
+		}
+	}
+
+	/*
+	 * If subchannels existed, do a full NVS/RNDIS teardown
+	 * and vmbus re-init to ensure a clean NVS session.
+	 * Cannot re-send NVS subchannel request on the same
+	 * session without invalidating the data path.
+	 */
+	if (old_subchans > 0) {
+		PMD_DRV_LOG(NOTICE,
+			    "reinit NVS (had %u subchannels)",
+			    old_subchans);
+
+		hn_chim_uninit(dev);
+		rte_free(hv->primary->rxbuf_info);
+		hv->primary->rxbuf_info = NULL;
+		hn_detach(hv);
+
+		rte_vmbus_chan_close(hv->channels[0]);
+		rte_free(hv->channels[0]);
+		hv->channels[0] = NULL;
+
+		rte_vmbus_unmap_device(hv->vmbus);
+		device_unmapped = true;
+		err = rte_vmbus_map_device(hv->vmbus);
+		if (err) {
+			PMD_DRV_LOG(ERR,
+				    "Could not re-map vmbus device!");
+			goto reinit_failed;
+		}
+		device_unmapped = false;
+
+		hv->rxbuf_res = hv->vmbus->resource[HV_RECV_BUF_MAP];
+		hv->chim_res  = hv->vmbus->resource[HV_SEND_BUF_MAP];
+
+		err = rte_vmbus_chan_open(hv->vmbus, &hv->channels[0]);
+		if (err) {
+			PMD_DRV_LOG(ERR,
+				    "Could not re-open vmbus channel!");
+			goto reinit_failed;
+		}
+
+		hv->primary->chan = hv->channels[0];
+
+		rte_vmbus_set_latency(hv->vmbus, hv->channels[0],
+				      hv->latency);
+
+		err = hn_attach(hv, dev->data->mtu);
+		if (err) {
+			rte_vmbus_chan_close(hv->channels[0]);
+			rte_free(hv->channels[0]);
+			hv->channels[0] = NULL;
+			PMD_DRV_LOG(ERR,
+				    "NVS reinit failed: %d", err);
+			goto reinit_failed;
+		}
+
+		err = hn_chim_init(dev);
+		if (err) {
+			hn_detach(hv);
+			rte_vmbus_chan_close(hv->channels[0]);
+			rte_free(hv->channels[0]);
+			hv->channels[0] = NULL;
+			PMD_DRV_LOG(ERR,
+				    "chim reinit failed: %d", err);
+			goto reinit_failed;
+		}
+	}
+
 	for (i = 0; i < NDIS_HASH_INDCNT; i++)
 		hv->rss_ind[i] = i % dev->data->nb_rx_queues;
 
 	hn_rss_hash_init(hv, rss_conf);
 
 	subchan = hv->num_queues - 1;
+
+	/* Allocate fresh subchannels and configure RSS */
 	if (subchan > 0) {
 		err = hn_subchan_configure(hv, subchan);
 		if (err) {
 			PMD_DRV_LOG(NOTICE,
 				    "subchannel configuration failed");
-			return err;
+			goto subchan_cleanup;
 		}
 
 		err = hn_rndis_conf_rss(hv, NDIS_RSS_FLAG_DISABLE);
 		if (err) {
 			PMD_DRV_LOG(NOTICE,
 				"rss disable failed");
-			return err;
+			goto subchan_cleanup;
 		}
 
 		if (rss_conf->rss_hf != 0) {

@@ -815,12 +895,82 @@ static int hn_dev_configure(struct rte_eth_dev *dev)
 			if (err) {
 				PMD_DRV_LOG(NOTICE,
 					    "initial RSS config failed");
-				return err;
+				goto subchan_cleanup;
 			}
 		}
 	}
 
+skip_reinit:
+	/* Apply offload config after reinit so it targets the final RNDIS session */
+	err = hn_rndis_conf_offload(hv, txmode->offloads,
+				    rxmode->offloads);
+	if (err) {
+		PMD_DRV_LOG(NOTICE,
+			    "offload configure failed");
+		return err;
+	}
+
 	return hn_vf_configure_locked(dev, dev_conf);
+
+subchan_cleanup:
+	for (i = 1; i < HN_MAX_CHANNELS; i++) {
+		if (hv->channels[i] != NULL) {
+			rte_vmbus_chan_close(hv->channels[i]);
+			hv->channels[i] = NULL;
+		}
+	}
+	hv->num_queues = 1;
+	for (i = 0; i < NDIS_HASH_INDCNT; i++)
+		hv->rss_ind[i] = 0;
+
+	/* Apply offload config so device is usable on primary queue */
+	hn_rndis_conf_offload(hv, txmode->offloads, rxmode->offloads);
+	return err;
+
+reinit_failed:
+	/*
+	 * Device is in a broken state after failed reinit.
+	 * Try to re-establish minimal connectivity.
+	 */
+	PMD_DRV_LOG(ERR,
+		    "reinit failed (err %d), attempting recovery", err);
+	if (hv->channels[0] == NULL) {
+		if (device_unmapped) {
+			if (rte_vmbus_map_device(hv->vmbus)) {
+				hv->num_queues = 0;
+				PMD_DRV_LOG(ERR,
+					    "recovery failed, could not re-map device");
+				return err;
+			}
+			hv->rxbuf_res = hv->vmbus->resource[HV_RECV_BUF_MAP];
+			hv->chim_res  = hv->vmbus->resource[HV_SEND_BUF_MAP];
+		}
+		if (rte_vmbus_chan_open(hv->vmbus, &hv->channels[0]) == 0) {
+			if (hn_attach(hv, dev->data->mtu) == 0) {
+				hv->primary->chan = hv->channels[0];
+				if (hn_chim_init(dev) != 0)
+					PMD_DRV_LOG(WARNING,
+						    "chim reinit failed during recovery");
+				hv->num_queues = 1;
+				PMD_DRV_LOG(NOTICE,
+					    "recovery successful on primary channel");
+			} else {
+				rte_vmbus_chan_close(hv->channels[0]);
+				rte_free(hv->channels[0]);
+				hv->channels[0] = NULL;
+				hv->num_queues = 0;
+				PMD_DRV_LOG(ERR,
+					    "recovery failed, device unusable");
+			}
+		} else {
+			hv->num_queues = 0;
+			PMD_DRV_LOG(ERR,
+				    "recovery failed, device unusable");
+		}
+	} else {
+		hv->num_queues = 1;
+	}
+	return err;
 }
 
 static int hn_dev_stats_get(struct rte_eth_dev *dev,

@@ -1073,6 +1223,7 @@ hn_dev_stop(struct rte_eth_dev *dev)
 {
 	struct hn_data *hv = dev->data->dev_private;
 	int i, ret;
+	unsigned int retry;
 
 	PMD_INIT_FUNC_TRACE();
 	dev->data->dev_started = 0;

@@ -1081,6 +1232,29 @@ hn_dev_stop(struct rte_eth_dev *dev)
 	hn_rndis_set_rxfilter(hv, 0);
 	ret = hn_vf_stop(dev);
 
+	/*
+	 * Drain pending TX completions to prevent stale completions
+	 * from corrupting queue state after port reconfiguration.
+	 */
+	for (retry = 0; retry < 100; retry++) {
+		uint32_t pending = 0;
+
+		for (i = 0; i < hv->num_queues; i++) {
+			struct hn_tx_queue *txq = dev->data->tx_queues[i];
+
+			if (txq == NULL)
+				continue;
+			hn_process_events(hv, i, 0);
+			pending += rte_mempool_in_use_count(txq->txdesc_pool);
+		}
+		if (pending == 0)
+			break;
+		rte_delay_ms(10);
+	}
+	if (retry >= 100)
+		PMD_DRV_LOG(WARNING,
+			    "Failed to drain all TX completions");
+
 	for (i = 0; i < hv->num_queues; i++) {
 		dev->data->tx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED;
 		dev->data->rx_queue_state[i] = RTE_ETH_QUEUE_STATE_STOPPED;

index 0ecfaf54ea..e77232bfb3 100644
@@ -637,12 +637,14 @@ void hn_vf_tx_queue_release(struct hn_data *hv, uint16_t queue_id)
 {
 	struct rte_eth_dev *vf_dev;
 
-	rte_rwlock_read_lock(&hv->vf_lock);
+	rte_rwlock_write_lock(&hv->vf_lock);
 	vf_dev = hn_get_vf_dev(hv);
-	if (vf_dev && vf_dev->dev_ops->tx_queue_release)
+	if (vf_dev && vf_dev->dev_ops->tx_queue_release) {
 		(*vf_dev->dev_ops->tx_queue_release)(vf_dev, queue_id);
+		vf_dev->data->tx_queues[queue_id] = NULL;
+	}
 
-	rte_rwlock_read_unlock(&hv->vf_lock);
+	rte_rwlock_write_unlock(&hv->vf_lock);
 }
 
 int hn_vf_rx_queue_setup(struct rte_eth_dev *dev,

@@ -669,11 +671,13 @@ void hn_vf_rx_queue_release(struct hn_data *hv, uint16_t queue_id)
 {
 	struct rte_eth_dev *vf_dev;
 
-	rte_rwlock_read_lock(&hv->vf_lock);
+	rte_rwlock_write_lock(&hv->vf_lock);
 	vf_dev = hn_get_vf_dev(hv);
-	if (vf_dev && vf_dev->dev_ops->rx_queue_release)
+	if (vf_dev && vf_dev->dev_ops->rx_queue_release) {
 		(*vf_dev->dev_ops->rx_queue_release)(vf_dev, queue_id);
-	rte_rwlock_read_unlock(&hv->vf_lock);
+		vf_dev->data->rx_queues[queue_id] = NULL;
+	}
+	rte_rwlock_write_unlock(&hv->vf_lock);
 }
 
 int hn_vf_stats_get(struct rte_eth_dev *dev,